astrofy-components
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data during the component creation and verification process.
- Ingestion points: In SKILL.md and references/technical.md, the agent is instructed to read .astro components, CSS styles, and consumer code files.
- Boundary markers: There are no instructions to use delimiters or ignore embedded prompts within the processed files.
- Capability inventory: The skill utilizes the astrofy check command and performs file-based modifications.
- Sanitization: The instructions do not specify any validation or sanitization for the ingested content.- [COMMAND_EXECUTION]: The skill instructs the agent to run the astrofy check --category components command to verify the implementation against established rules.
Audit Metadata